🧠 MindStat

⚠️ Example not found

This example does not exist or may have been moved.

Browse all examples
🔗
Correlation

Point-Biserial Correlation — Binary × Continuous

Express a two-group comparison as a correlation between a 0/1 group code and a continuous outcome. Shows the exact mathematical equivalence to the independent t-test.

📊 r_pb(10) = .904, p < .001
Step-by-step solution

🔗 34 · Point-Biserial Correlation — Binary × Continuous

Treatment Group and Outcome Score — the Correlation View of a t-test
Correlation
Research Question: 12 participants were split into a Control group and a Treatment group (n=6 each). Instead of running an independent t-test, we can express the same relationship as a correlation between group membership (0/1) and outcome score.
Participant Group (0=Control, 1=Treatment) Score
1072
2068
3075
4070
5074
6069
7182
8188
9179
10185
11190
12184
Point-biserial r is just Pearson's r applied to a 0/1 group code
r p b = ( g i g ¯ ) ( y i y ¯ ) ( g i g ¯ ) 2 ( y i y ¯ ) 2
  1. 1
    Group means:
    y ¯ C o n t r o l = 71.33 , y ¯ T r e a t m e n t = 84.67
  2. 2
    Compute Pearson's r between the 0/1 group code and score, exactly as with any two continuous variables:
    r p b = .904
  3. 3
    Significance test:
    t = r p b d f 1 r p b 2 = .904 10 1 .818 = 6.704 , d f = 10 ,   p < .001
  4. 4
    Teaching point — this is the same test as the independent t-test: This t and df are identical to what an independent-samples t-test on Control vs. Treatment would give — point-biserial r is mathematically the correlation-equivalent view of the same comparison, not a separate result.
.904
r_pb
6.704
t(10)
<.001
p
.818
r²_pb
🔴 Significant — r_pb(10) = .904, p < .001. Treatment-group membership is strongly associated with higher scores.
APA-7
A point-biserial correlation revealed a strong positive association between treatment-group membership and outcome score, r_pb(10) = .904, p < .001, with the treatment group (M = 84.67) scoring markedly higher than the control group (M = 71.33).